System and method for reducting or eliminating artifacts in magnectic resonance imaging

Abstract

A computer-implemented method for reducing or eliminating artifacts in MRI, includes steps of: S1: acquiring a plurality of MR signals mixed with EMI with different weightings from a plurality of receiver elements of at least one array coil; S2: obtaining EMI eliminated MR signals for each receiver element based on the MR signals mixed with EMI obtained in step S1; and S3: obtaining MR image based on the EMI eliminated MR signals obtained in step S2.

What is claimed is: 
     
         1 . A computer-implemented method for reducing or eliminating artifacts in MRI, comprising the steps of:
 S1: acquiring a plurality of MR signals mixed with EMI with different weightings from a plurality of receiver elements of at least one array coil;   S2: obtaining EMI eliminated MR signals for each receiver element based on the MR signals mixed with EMI obtained in step S1; and   S3: obtaining MR image based on the EMI eliminated MR signals obtained in step S2.   
     
     
         2 . The method of  claim 1 , further comprises a step of:
 optimizing at least one of the receiver elements to mainly detect EMI signals from broad range of sources with high sensitivity along three different polarization directions through coil designs and their spatial distribution.   
     
     
         3 . The method of  claim 1 , wherein the receiver elements are arranged at different locations and/or orientations. 
     
     
         4 . The method of  claim 1 , wherein at least one coil of the at least one array coil has different receiving RF coil design, RF polarization orientation, location and/or different sensitivity to EMI and MR signal. 
     
     
         5 . The method of  claim 1 , wherein the at least one array coil comprises a plurality of array coils arranged at different locations and/or orientations. 
     
     
         6 . The method of  claim 1 , wherein the step S2 is implemented with blind source separation. 
     
     
         7 . The method of  claim 6 , wherein the step S2 comprises the steps of:
 S21: estimating mixing/unmixing matrix based on the MR signals mixed with EMI;   S22: identifying EMI and noise from unmixed sources;   S23: setting the weightings for EMI and noise related sources to zero; and   S24: obtaining EMI eliminated MR signal by re-mixing the sources using estimated mixing matrix.   
     
     
         8 . The method of  claim 7 , wherein in step S21, independent component analysis is used to estimate the mixing matrix. 
     
     
         9 . The method of  claim 8 , wherein the independent component analysis implemented with fixed-point algorithm with projection pursuit, or informax algorithm which finds independent signals by maximizing the entropy. 
     
     
         10 . The method of  claim 7 , wherein in step S21, principal component analysis is used to estimate the mixing matrix. 
     
     
         11 . The method of  claim 10 , wherein the principal component analysis is implemented by eigenvalue decomposition of a data covariance or correlation matrix, or singular value decomposition of a data matrix. 
     
     
         12 . The method of  claim 1 , wherein the Step S2 is implemented by means of deep learning model. 
     
     
         13 . The method of  claim 1 , wherein the Step S2 comprises steps of:
 S25: designing and training a deep learning model to establish relationships between EMI signals sampled by different receiver elements within each of the at least one array coil in absence of any MR signal, from which EMI signals from a group of receiver elements are estimated from EMI signals in other receiver elements; and   S26: for each set of actual measurements obtained from during a specific subject MRI scan, feeding the MR signals acquired in step S1 to the trained model to estimate the EMI in the MR signals.   
     
     
         14 . The method of  claim 12 , wherein in step S2, a neural network architecture is designed, which inputs the MR signals mixed with EMI acquired in step S1, and outputs EMI eliminated MR signals. 
     
     
         15 . The method of  claim 12 , wherein in step S2, a neural network architecture is designed, which inputs the MR signals mixed with EMI acquired in step S1, and outputs EMI, and wherein the step S2 further comprises a step of subtracting the EMI output from the MR signals mixed with EMI obtained in step S1. 
     
     
         16 . The method of  claim 1 , further comprises a step of:
 adjusting coil sensitivity to EMT of directions X, Y, and Z of the at least one array coil.   
     
     
         17 . A computer-implemented method for reducing or eliminating artifacts in MRI, comprising steps of:
 S1: acquiring a plurality of MR signals mixed with EMI with different weightings from a plurality of receiver elements of at least one array coil;   S25: designing and training a deep learning model to establish relationships between EMI signals sampled by different receiver elements within each of the at least one array coil in absence of any MR signal, from which EMI signals from a group of receiver elements are estimated from EMI signals in other receiver elements; and   S26: for each set of actual measurements obtained from during a specific subject MRI scan, feeding the MR signals acquired in step Si to the trained model to estimate the EMI in the MR signals and outputting reconstructed MR images.   
     
     
         18 . The method of  claim 1 , wherein the deep learning model is designed as a neural network architecture, and the neural network architecture is an artificial neural network, a convolutional neural network, or a generative adversarial network. 
     
     
         19 . A system for reducing or eliminating artifacts in MRI, comprising:
 at least one array coil having a plurality of receiver elements;   at least one computer hardware processor;   at least one non-transitory computer-readable storage medium; and   at least one computer program stored in the at least one non-transitory computer-readable storage medium and executable on the at least one computer hardware processor,   wherein when executing the at least one computer program, the at least one computer hardware processor implements the method according to  claim 1 .   
     
     
         20 . The system of  claim 19 , wherein the at least one computer program comprises:
 acquisition module, configured to acquire MR signals mixed with EMI with different weightings from at least two receiver elements of the at least one array coil; and   separation module, configured to separate the MR signals and the EMI of the MR signals mixed with EMI obtained from the acquisition module.